Back to Search
Start Over
Differentiable Surface Splatting for Point-based Geometry Processing
- Publication Year :
- 2019
-
Abstract
- We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for point clouds. Gradients for point locations and normals are carefully designed to handle discontinuities of the rendering function. Regularization terms are introduced to ensure uniform distribution of the points on the underlying surface. We demonstrate applications of DSS to inverse rendering for geometry synthesis and denoising, where large scale topological changes, as well as small scale detail modifications, are accurately and robustly handled without requiring explicit connectivity, outperforming state-of-the-art techniques. The data and code are at https://github.com/yifita/DSS.<br />Comment: This version is contains camera-ready manuscript for SIGGRAPH Asia 2019
- Subjects :
- Computer Science - Graphics
Computer Science - Neural and Evolutionary Computing
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.1906.04173
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1145/3355089.3356513